Supervised learning in spiking neural networks with FORCE training.
Supervised learning in spiking neural networks with FORCE training.
复制标题
DOI：
10.1038/s41467-017-01827-3
复制
发表时间：
2017-12-20
影响因子：
16.6
通讯作者：
Clopath C
中科院分区：
文献类型：
--
作者：
Nicola W;Clopath C
神经元群体在它们影响和显示的行为中表现出非凡的多样性。最近出现的机器学习技术使我们能够创建模型神经元网络，这些网络显示出类似复杂性的行为。在这里，我们证明了这样一种技术，FORCE方法，尖峰神经网络的直接适用性。我们训练这些网络来模仿动态系统，对输入进行分类，并存储与歌曲音符相对应的离散序列。最后，我们使用FORCE训练来创建两个生物激励的模型电路。其中一个是受斑胸草雀的启发，成功地再现了鸣禽的歌声。第二个网络由海马体驱动，并被训练来存储和重放电影场景。FORCE训练的网络再现的行为在复杂性上与其启发的电路相当，并产生用其他技术不易获得的信息，例如对药理学操作的行为反应和尖峰时间统计。训练是A。在这里，作者在尖峰神经元网络模型中实现了FORCE训练，并证明这些网络可以被训练成表现出不同的动态行为。
Populations of neurons display an extraordinary diversity in the behaviors they affect and display. Machine learning techniques have recently emerged that allow us to create networks of model neurons that display behaviors of similar complexity. Here we demonstrate the direct applicability of one such technique, the FORCE method, to spiking neural networks. We train these networks to mimic dynamical systems, classify inputs, and store discrete sequences that correspond to the notes of a song. Finally, we use FORCE training to create two biologically motivated model circuits. One is inspired by the zebra finch and successfully reproduces songbird singing. The second network is motivated by the hippocampus and is trained to store and replay a movie scene. FORCE trained networks reproduce behaviors comparable in complexity to their inspired circuits and yield information not easily obtainable with other techniques, such as behavioral responses to pharmacological manipulations and spike timing statistics. FORCE training is a . Here the authors implement FORCE training in models of spiking neuronal networks and demonstrate that these networks can be trained to exhibit different dynamic behaviours.
登录
查看更多内容
影响因子：
4.3
作者：
Boerlin M;Machens CK;Denève S
通讯作者：
Denève S
影响因子：
3.5
作者：
Buzsáki, G
通讯作者：
Buzsáki, G
影响因子：
25
作者：
Abbott LF;DePasquale B;Memmesheimer RM
通讯作者：
Memmesheimer RM
影响因子：
4.3
作者：
Harish O;Hansel D
通讯作者：
Hansel D
影响因子：
56.9
作者：
Eliasmith, Chris;Stewart, Terrence C.;Rasmussen, Daniel
通讯作者：
Rasmussen, Daniel